technology

OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks

6 Haziran 2026TechCrunch
  • Even with Lockdown Mode, ChatGPT could be still vulnerable to prompt injections, but the goal is to reduce the likelihood that sensitive data gets shared in the process.
  • Published 8 minutes ago, this story falls under technology coverage. Follow updates from TechCrunch for related developments.
NewsAI özeti

ℹ️ This article was automatically processed by NewsAI. A standard summary is shown while the AI service is temporarily unavailable.